© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9827
    Prev
    Next
    INDEX
    Explanations

    legal documents mentioning the state of Mississippi

    oai_token-act-pair · gemini-2.0-flash

    Mississippi legal references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    medriver
    -0.49
    anele
    -0.49
    Revenir
    -0.49
     createContext
    -0.45
     paik
    -0.45
    tachten
    -0.44
     remboursement
    -0.43
    CreateMap
    -0.43
     créativité
    -0.43
     prosím
    -0.43
    POSITIVE LOGITS
     viewDidLoad
    0.75
    دانشنامهٔ
    0.73
     Khas
    0.65
     ویکی‌پدی
    0.63
     تضيفلها
    0.61
     Biôgrafia
    0.60
    Personensuche
    0.60
    IsMutable
    0.60
     Bioaccumulative
    0.58
    ########.
    0.56
    Activations Density 0.997%

    No Known Activations